Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3095 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5673. Min Range: -0.5673

Max Act: 0.5673. Min Act: -0.0001

Data Index: 1130247 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.5673. Min Range: -0.5673

Max Act: 0.4817. Min Act: -0.0001

Data Index: 1524419 (Python Code)

Max Activating Token Index: 868

Text #2

Max Range: 0.5673. Min Range: -0.5673

Max Act: 0.4483. Min Act: -0.0001

Data Index: 1391375 (Python Code)

Max Activating Token Index: 479

Text #3

Max Range: 0.5673. Min Range: -0.5673

Max Act: 0.4749. Min Act: -0.0001

Data Index: 1571365 (Python Code)

Max Activating Token Index: 886

Text #4

Max Range: 0.5673. Min Range: -0.5673

Max Act: 0.4591. Min Act: -0.0001

Data Index: 923669 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 0.5673. Min Range: -0.5673

Max Act: 0.4769. Min Act: -0.0000

Data Index: 524210 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.5673. Min Range: -0.5673

Max Act: 0.4512. Min Act: -0.0001

Data Index: 385101 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.5673. Min Range: -0.5673

Max Act: 0.4699. Min Act: -0.0001

Data Index: 66422 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 0.5673. Min Range: -0.5673

Max Act: 0.4171. Min Act: -0.0001

Data Index: 334247 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.5673. Min Range: -0.5673

Max Act: 0.4398. Min Act: -0.0001

Data Index: 917380 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 0.5673. Min Range: -0.5673

Max Act: 0.4157. Min Act: -0.0001

Data Index: 82539 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.5673. Min Range: -0.5673

Max Act: 0.4103. Min Act: -0.0001

Data Index: 1336797 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 0.5673. Min Range: -0.5673

Max Act: 0.3982. Min Act: -0.0000

Data Index: 1608559 (Python Code)

Max Activating Token Index: 664

Text #13

Max Range: 0.5673. Min Range: -0.5673

Max Act: 0.4199. Min Act: -0.0000

Data Index: 143138 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 0.5673. Min Range: -0.5673

Max Act: 0.4221. Min Act: -0.0001

Data Index: 1362023 (Python Code)

Max Activating Token Index: 45

Text #15

Max Range: 0.5673. Min Range: -0.5673

Max Act: 0.4288. Min Act: -0.0001

Data Index: 1127249 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.5673. Min Range: -0.5673

Max Act: 0.4487. Min Act: -0.0001

Data Index: 697460 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 0.5673. Min Range: -0.5673

Max Act: 0.3989. Min Act: -0.0000

Data Index: 409536 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.5673. Min Range: -0.5673

Max Act: 0.3963. Min Act: -0.0001

Data Index: 1239352 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 0.5673. Min Range: -0.5673

Max Act: 0.4418. Min Act: -0.0000

Data Index: 521725 (C4 (Web Text))

Max Activating Token Index: 554